We went to XPrize!
Our Dexterous Hands on a mobile manipulator made it to the finals of ANA Avatar XPRIZE competition!
Shadow Robot & Mobile Manipulation
Shadow’s Dexterous Hand system is designed for integration onto your robot platform.
Built from the ground up for ROS and used widely by researchers and developers to enable mobile robots for research and applications! Shadow has decades of experience enabling robotics researchers to deliver manipulation where they need it most.
More than just an end effector
Grasping unusually shaped objects - The Dexterous Hand is able to pick up a wider range of objects than a simple gripper
Dexterous - Multiple separately controlled joints on each finger and the thumb allow you to perform more controlled grasping and enables complex interactions with objects
Tactile sensor fittings - we can supply COTS tactile sensors or the documentation for you to install ones from your own lab
Intuitive ergonomics - If you want to work out how the robot should do something, just try it with your own hands! This also makes teleoperation easier for the operator
Support throughout the project - Shadow’s team have years of experience developing robot systems so we “feel your pain” when you run into challenges!
Meeting the needs of a Mobile Manipulator
Light - Our Dexterous Hand Lite is suitable for a 2.4kg payload arm, whilst delivering performance comparable to our Dexterous hand plus
Compact - The Hand Lite is shorter and lighter than the five-fingered Dexterous Hand, reducing the load on the robot arms - as you can see in the diagram
Power Efficient - Stepping down from the five-fingered hand to Hand Lite produces a 35% power saving, helping increase battery life on your mobile system.
Mobile - The small size and weight of Hand Lite make it easy to transport and mount on a mobile system, making it the perfect choice for mobile manipulation!
Affordable - Hand Lite is 35% cheaper than the full Shadow Dexterous Hand!
Dexterous Hand Lite
Case studies
OpenAI
We’ve worked with OpenAI, founded by business tycoons, Elon Musk and Sam Altman to advance research within AI and machine learning using the Shadow Dexterous Hand.
- OpenAI used the Shadow Hand to study ways of learning dexterity using the complex task of solving a Rubik’s cube single-handedly.
- They trained their system entirely in simulation via reinforcement learning.
- Shadow Dexterous Hand demonstrated the learnings in the real world. No fine-tuning needed.
- Featured on BBC News and the front page of the New York Times.
Click Here
Case studies
Human Brain Project (HBP)
HBP and Maastricht University successfully integrate and simulate the Shadow Hand on the HBP Neurorobotics Platform which connects a physics simulator to a variety of neural networks (or brains).
- The Human Brain Project added the virtual Shadow Hand to their EBRAINS infrastructure to learn more about how the brain coordinates complex hand movements.
- Each Shadow Hand joint can be individually linked to both the input and/or output of the brain.
- Contact-based feedback is forwarded to the brain. No need for time-consuming physical setups.
Click Here
Case studies
Google Brain
Google Brain used the Shadow Hand to learn how to manipulate multiple objects using just a few hours of real-world data.
- The team used a novel robot task planning technique involving deep dynamics models (DDM).
- They were able to manipulate multiple objects with just four hours of real-world data.
- More info about the impressive results in this article.
Click Here
Previous slide
Next slide
Learn more about our Dexterous Hand Lite
The dexterity factor of our Flagship Shadow Dexterous Hand in a smaller package.
Specifications Dexterous Hand Lite
PDF, 800KB
Interact
Grasping any shape
Interact with all the objects a human can – in particular, we test with the full YCB object set
Sense
Tactiles
Position sensing for accurate finger placement, tendon sensing to understand the effort exerted, and the option to add touch sensing at the fingertips
Think
Wealth of data
Over 80 sensors at 1kHz give you a wealth of data from the Hand Lite (over 130 on the full Hand) to enable your robot to truly “think” about grasping and manipulation!
Putting together a Mobile Manipulator?
Do you need a robot hand for a mobile manipulator?
Get in touch with us.